Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2969 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1632. Min Act: -0.0000

Data Index: 717639 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1359370 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1819500 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1922613 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1329. Min Act: -0.0000

Data Index: 844909 (The Pile)

Max Activating Token Index: 339

Text #5

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1589173 (The Pile)

Max Activating Token Index: 221

Text #6

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1311. Min Act: -0.0000

Data Index: 947954 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1307. Min Act: -0.0000

Data Index: 540828 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1369. Min Act: -0.0000

Data Index: 706131 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1380. Min Act: -0.0000

Data Index: 471980 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1277. Min Act: -0.0000

Data Index: 198648 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1235. Min Act: -0.0001

Data Index: 800741 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1307. Min Act: -0.0000

Data Index: 281654 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1538897 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1327. Min Act: -0.0000

Data Index: 355981 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1332. Min Act: -0.0000

Data Index: 611796 (The Pile)

Max Activating Token Index: 421

Text #16

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1260676 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1866876 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1255. Min Act: -0.0000

Data Index: 510883 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1155. Min Act: -0.0000

Data Index: 85691 (The Pile)

Max Activating Token Index: 626